remote
AI Backend Engineer (RAG / LLM)
AI Backend Engineer (RAG / LLM)
This is a full-time remote role for an AI Backend Engineer (RAG / LLM) focused on designing, developing, and maintaining scalable and efficient backend systems. Key responsibilities include building APIs, optimizing database performance, managing servers, integrating third-party services, and collaborating with frontend developers. The role requires strong experience in Python backend development, LLM-powered applications, databases, and cloud platforms.
About the role
Role Description
This is a full-time Remote role for an AI Backend Engineer (RAG / LLM). The Backend Engineer will design, develop, and maintain scalable and efficient backend systems. Responsibilities include building APIs, optimizing database performance, managing servers, integrating third-party services, and collaborating with frontend developers to ensure seamless functionality. The role also involves identifying and resolving technical challenges to deliver reliable solutions.
Basic Qualifications (Must-Have)
- 3–7 years of experience in backend engineering using Python
- Strong hands-on experience with FastAPI, Flask, or similar backend frameworks
- Proven experience building LLM-powered applications (RAG, LangChain, LlamaIndex, or similar)
- Experience designing and implementing REST APIs and microservices architectures
- Hands-on experience with databases (PostgreSQL, MongoDB) and caching systems (Redis)
- Experience working with vector databases or semantic search systems (Pinecone, FAISS, Chroma, pgvector)
- Strong understanding of system design, asynchronous processing, and scalable backend systems
- Experience with Docker and deploying services on cloud platforms (AWS, GCP, or Azure)
Preferred Qualification
- Experience building agentic or multi-agent AI systems (LangGraph, AutoGen, CrewAI)
- Experience with document processing pipelines (OCR, parsing, information extraction)
- Familiarity with retrieval optimization, ranking, and evaluation frameworks
- Experience with message queues / distributed systems (Kafka, Celery, RabbitMQ)
- Experience building multi-tenant SaaS systems with RBAC and audit logging
- Exposure to LLM evaluation, guardrails, and latency optimization